© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 3768
    Prev
    Next
    INDEX
    Explanations

    now or anymore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     fraudulently
    0.50
     rued
    0.50
    άσ
    0.49
    нов
    0.47
    джа
    0.46
     ridiculed
    0.45
    ել
    0.45
    ẏ
    0.45
    FAR
    0.45
    OCK
    0.44
    POSITIVE LOGITS
       
    0.51
    la
    0.51
     NO
    0.50
    3
    0.50
    ![
    0.49
    5
    0.48
     everything
    0.48
    sa
    0.48
     EVERYTHING
    0.47
    ↵
    0.47
    Activations Density 0.000%

    No Known Activations